Upload
blaise-merritt
View
220
Download
3
Embed Size (px)
Citation preview
Implementing Deduplication Tool For Storage Device Using
Sparse Indexing
Chunking
Introduction
……
Data Stream
……
……
Chunks(static size)
Chunks(variable size)
Fingerprinting-Deduplicating
Introduction
A
Storage
A G T
DataNew Data
Compare
If ‘A’ exists in the storage, ‘A’ won’t be written.
A C ……
Remove a copyand Share ‘A’.
Original Data
Fingerprinting(using hash function)
Overall Architecture
Dataset- 파일의 모음
- (*.exe, *.txt, *.jpg, *.mp3 …)
중복 데이터 분석 툴(CHUNKING - FINGERPRINTING -
SAMPLING - DEDUPLICATING)
입력
출력
분석 결과(deduplication factor, elpased
time …by variable criteria)
Experiment Criteria- Chunk Size(4kb, 8kb…)- Segment Size- Sampling Rate- Variability of Chunk, Seg-ment
Windows XP, 7C++
Development Environment
Schedule
1주 2주 3주 4주
3 월 Background Study(Reading Paper… ETC)
4 월 Implementing & Debugging Deduplication Tool
5 월 Implementing & Debug-ging
Experiments & Report
6 월